Table of Contents

Introducing Synopsys Cloud

Cloud native EDA tools and pre-optimized hardware platforms. Experience unlimited EDA licenses with true pay-per-use on an hourly or per-minute basis.

Let’s examine whether the EDA industry is ready for cloud computing and whether the cloud is ready for chip design and verification. 

Although cloud computing has existed for decades, many organizations are still not taking advantage of its business efficiencies, benefits, and competitive advantages. Instead, they rely on expensive, inflexible on-premises equipment and tools.


Security Concerns of Cloud Computing

The security of IP and confidential data in the cloud has been a primary concern for chip makers. Many believed that IP and data were not safe in someone else’s infrastructure.

Yet, cloud service providers (CSPs) invest far more in security than any enterprise. And as threat landscapes evolve, organizations must continually respond.

CSPs now offer automated tools and state-of-the-art best practices, such as data encryption in transit and at rest. For major cloud providers, security has become a core competency integrated throughout their infrastructure to protect against threats. As a result, CSP security teams often are larger than most companies’ entire IT staff.


Complexity Compels the Move to the Cloud

Because of the complexity of modern chip design and verification, chip makers have been compelled to use the cloud despite concerns. Chip design complexity has dramatically increased in response to the explosion of big data and market pressures from expanding applications—including:

Design complexity is exacerbated by high-performance, low-power, and area IPs used as building blocks for systems-on-a-chip (SoC).

Consequently, on-premises compute capacity has become an undeniable bottleneck for chip design teams to design and verify their IP designs and bring their SoC to market faster. These teams are being pushed to use cloud computing for the design and verification of modern SoCs.


Cloud Computing Deployment

Before we examine how cloud computing can help with chip-making complexity, let’s take a look at the three main cloud deployment types:

  • Public Clouds. Third parties provide computing resources, such as servers and storage, over the internet. All hardware, software, and other infrastructure are owned and managed by public cloud providers, such as Amazon Web Services, Microsoft Azure, and Google Cloud.
  • Private Clouds. Only one organization uses cloud computing resources. A private cloud can be deployed in the company’s data center or off-premises at a third-party facility. Private clouds provide the benefits of public clouds, including self-service, scalability, and elasticity, as well as control and customization. 
  • Hybrid Clouds. Combine public and private clouds that share data and applications. You can move data and applications between private and public clouds using hybrid clouds for enhanced flexibility and deployment options. Private clouds can store confidential data and IP, while public clouds can host web servers and endpoints.
Cloud Computing Deployment Models | Synopsys Cloud

Cloud Computing Features for Chip Design

Chip designers are turning to the cloud to drive innovation and productivity. Cloud computing gives you the flexibility to scale your design and verification capabilities whenever you need them. The results will be faster, higher quality, and more affordable chips.

Chip design teams can access the best computing and storage resources through cloud computing. With pay-as-you-go models, chip designers can ramp up quickly. Listed below are essential features of cloud computing for chip design and verification.

 

Scalability

Cloud-based systems can be scaled up in minutes. As a result, you can quickly expand or reduce your EDA infrastructure based on demand. You can request more capacity from the cloud service within minutes and reduce it just as quickly. To add more EDA capacity to your on-premises network, you need to reassign existing resources or add servers. 

 

Network Segmentation 

Large chip makers commonly employ several design centers worldwide. Laws or contracts may require IP to stay within specific geographical boundaries. Cloud networks can enforce geography-based rules using network segmentation to meet these requirements.

 

Redundancy  

With cloud systems, redundant servers are located in data centers and across the globe; on-premises networks cannot compete. One advantage of cloud redundancy is that it provides protection from localized disasters for data in the cloud. 

 

Single Point of Failure

There are usually several points of failure in EDA grids. A central job dispatcher, for example, runs on a single node. All EDA work halts if that node is disrupted. The same applies to EDA licenses, configuration management, and version-control servers. Cloud networks are based on microservices, so they don’t suffer from single-point-of-failure vulnerabilities like on-premises networks.

Ease of Use

On-premises EDA users should find the cloud much easier to use. As a result of on-demand, real-time provisioning, the cloud offers faster turnaround times. Often, the user doesn’t need special knowledge or processes to implement EDA tools in the cloud. 

 

Cost

EDA software can run in the cloud without extensive processing power and run-time infrastructure investments. Maintenance and support costs also can be eliminated. With the cloud, transitions between low and high-demand periods can be invisible to the end user. 

 

Time to Market

Cloud computing allows you to keep pace with the growing computing demands to speed time to market. As chip design teams acquire compute resources more rapidly, they can complete more iterations daily, reducing time spent on verification, reliability checks, and simulations.

 

Emergencies

Cloud-based EDA technology can help you respond quickly and effectively to late-breaking emergencies. With cloud computing, you can resolve critical issues without causing significant disruptions. 

 

Workflow Efficiency

You can reduce network latency by choosing cloud servers that are nearby. In addition to improving performance, cache-based systems are also more efficient.  

 

Innovation

Cloud customers can use automation, artificial intelligence (AI), and other advanced tools in the chip design process to enable innovation. In addition to boosting productivity and innovation, these tools can complement design expertise. 


How Can Synopsys Help You Leverage the Cloud

Synopsys is committed to providing fast, secure, and efficient EDA cloud solutions to accelerate your cloud journey. Silicon chip design and verification are enhanced using our cloud-optimized flows. Synopsys also works closely with public cloud vendors such as Microsoft Azure, Google Cloud Platform, and Amazon Web Services to optimize your experience. Since we assist cloud vendors in developing high-performance computing (HPC) SoCs, we understand what designers require in terms of EDA to produce chips for HPC workloads.

Cloud-based EDA solutions from Synopsys enable continual innovation, resulting in faster, less expensive, and better chips. Cloud EDA software gives you the productivity, scalability, security, and flexibility you need to design and verify chips in the cloud and migrate your software applications to the cloud. You can experience the benefits of cloud-based chip design with our cloud-ready design, verification, and IP solutions:

  • Faster time to market. We have solutions that have been production tested on major public cloud platforms and are endorsed by large semiconductor foundries.
  • Improved chip quality. Our cloud-based solutions offer massive elasticity and scalability.
  • Cost-effective. Our solutions are designed to take advantage of cost-optimized spot instances in the cloud.

Synopsys Tools

With Synopsys Cloud, you can access unlimited EDA software licenses on-demand and focus on what you do best—designing chips. We have reinvented the future of chip design with cloud-native EDA tools, pre-optimized hardware platforms, and a modern customer experience.

Synopsys Cloud offers:

  • Unlimited EDA licenses. Select and use the tools and compute resources you need without being limited by traditional licenses.
  • Pre-optimized compute flows. Accelerate time-to-results at any scale, wherever you are.
  • Exponential compute power. Run design and verification jobs faster with limitless compute and flexible software-as-a-service (SaaS) and bring-your-own-cloud (BYOC) deployment options.
  • SaaS. Design and verify chips in the cloud without building infrastructure or managing license servers. We use a single contract that provides access to the required software, hardware, and expert support. SaaS includes the following EDA tools:
    • RTL and gate-level simulations
    • Static timing analysis
    • Physical verification
    • Robust cloud-optimized flows
  • Bring Your Own Cloud (BYOC). Take advantage of Synopsys Cloud’s unlimited access to EDA tools through a true pay-per-use pricing model by working directly with the major cloud providers. You can run the same flows with your existing scripts.

Synopsys Cloud’s FlexEDA Model

With Synopsys Cloud’s FlexEDA model, you can access our EDA applications on-demand and run unlimited parallel jobs and regressions using cloud pay-per-use technology. FlexEDA enables all resources to be accessible anytime, without arbitrary resource constraints.

The FlexEDA model is based on unlimited EDA license availability with true pay-per-use hourly or minute-by-minute. Designers plan, schedule, and run specific EDA jobs based on where they are in the design cycle and their power, performance, and area goals. The EDA software is scaled automatically according to the elastic cloud infrastructure enabled by the designer.

The FlexEDA model is leverages the following architectural elements:

  • By using metering technology, on-demand EDA tools are now available without changing the EDA software code.
  • EDA workloads are pre-optimized. We benchmarked and tested hundreds of compute virtual machines available in the public cloud for EDA workloads.
  • We provide deep integration with cloud stacks so you can benefit from auto-scaling, fault-tolerance, and metering capabilities.
  • We provide access to all EDA workloads through a browser and a platform with native scheduling, virtual desktops, and project and user management capabilities.
  • The CSP’s shared responsibility model is elevated through in-depth security with a fully integrated architecture to ensure customer data and IP are protected at all levels.
  • Customers who prefer to run and manage their public cloud environments can use FlexEDA in a BYOC deployment model.

We believe FlexEDA will shape the future of EDA because of its flexibility in pricing and licensing without predefined infrastructure constraints or license quantity commitments. Synopsys Cloud FlexEDA lets designers approach each project differently, so that chip design and verification tools can be used according to design needs. 


Synopsys, EDA, and the Cloud

Synopsys is the industry’s largest provider of electronic design automation (EDA) technology used in the design and verification of semiconductor devices, or chips. With Synopsys Cloud, we’re taking EDA to new heights, combining the availability of advanced compute and storage infrastructure with unlimited access to EDA software licenses on-demand so you can focus on what you do best – designing chips, faster. Delivering cloud-native EDA tools and pre-optimized hardware platforms, an extremely flexible business model, and a modern customer experience, Synopsys has reimagined the future of chip design on the cloud, without disrupting proven workflows.

 

Take a Test Drive!

Synopsys technology drives innovations that change how people work and play using high-performance silicon chips. Let Synopsys power your innovation journey with cloud-based EDA tools. Sign up to try Synopsys Cloud for free!

Continue Reading